-
The Model Context Protocol (MCP) published its 2026-07-28 specification, the largest revision since launch: MCP is now stateless, with a governed extensions system and hardened authorization. Learn what changed and how to enable the new version on Amazon Bedrock AgentCore Gateway with a single UpdateGateway call. Link …
Read More -
Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore. This post walks through a market surveillance example with state-driven orchestration, checkpoint-based recovery, and AgentCore memory and …
Read More -
A new field report shows how scientists use AI coding agents to modernize scientific computing, accelerating software development and discovery in genomics and beyond. Link to article: https://openai.com/index/scientific-computing-agentic-ai
Read More -
A recent conversation started (as many interesting conversations do) with a simple question: "Why is MSIX secure?" MSIX includes multiple layers of protection designed to defend against both accidental damage and malicious tampering. But as with all good security solutions, it's not the individual elements so …
Read More -
The best AI assistance is the kind you can steer, understand, and rely on. The July update is built around all three. There's a new Agent (Preview) in Copilot Chat, built on the same GitHub Copilot SDK that powers the GitHub Copilot CLI, that gets more done with less back-and Link to article: …
Read More -
Great code has a long memory. The fix you shipped last quarter, the refactor that touched a dozen files, the one-line change that explained why something works the way it does — it's all there in your commit history. The hard part has always been finding it. Today, we're excited to announce that Commit Search is …
Read More -
Many enterprises still maintain legacy Visual Basic .NET (VB.NET) applications built on .NET Framework. While these applications continue to serve business needs, organizations face growing challenges: a shrinking VB.NET developer talent pool, limited modern tooling support, and a difficult path to cross-platform .NET …
Read More -
Part 3 of a series where we take public “token saver” add-ons for coding agents and run the same paired A/B benchmark against each of them. Part 1 was the caveman skill (advertised −65%, measured −8.5%). Part 2 was rtk (advertised −60–90%, measured +7.6%). We ran 80 paired tasks to test the ponytail skill for […] Link …
Read More -
SQL database projects are a fundamental tool for keeping your database in source control, tracking changes and collaborating on quickly evolving database needs. Not to be forgotten, their superpower is being able to dynamically generate deployment scripts that match the dec Link to article: …
Read More -
Clean architecture vs modular monolith in C# -- understand the key differences, when each applies, and why combining them is often the most powerful approach for .NET developers. Link to article: https://www.devleader.ca/2026/07/28/clean-architecture-vs-modular-monolith-in-c-whats-the-difference
Read More -
Learn how AI coding agents can expose credentials in supply chain attacks and how Docker Sandboxes keep secrets out of an agent's reach. Link to article: https://www.docker.com/blog/coding-agent-horror-stories-the-29-million-secret-problem/
Read More -
CI/CD is changing rapidly. Or is it?.. AI-assisted development is increasing the volume of code being written, software systems are becoming more distributed, and engineering teams are continuously rethinking how they build, test, and ship applications. At the same time, organizations are modernizing their CI/CD …
Read More -
Your agents can now discover and load Agent Skills directly from a Model Context Protocol (MCP) server. Instead of shipping every skill inside your application or copying skill folders into each deployment, you point an agent at an MCP server and it pulls the skills it needs on demand. A central team can p Link to …
Read More -
TL;DR KotlinLLM is now public. It’s a research prototype for delegating runtime logic to an LLM from Kotlin code. Instead of calling an LLM on every request or running a separate agent, you can write an explicit Kotlin call. Its body is generated Kotlin source code, and that code is updated as your application hits […] …
Read More -
A practical guide to OpenTelemetry metrics .NET -- covering Meter, Counter, Histogram, ObservableGauge, IMeterFactory, and exporting to Prometheus or OTLP. Link to article: https://www.devleader.ca/2026/07/27/opentelemetry-metrics-net-counters-histograms-and-imeterfactory
Read More -
Writing a query that works is easy. Writing a query that scales is a different story. Link to article: https://devblogs.microsoft.com/documentdb/query-performance-tuning-guide
Read More -
Most of the big improvements in this blog post came from JasperFx client engagements. Reach out any time to sales@jasperfx.net and we’ll happily chat with you about how we can help your shop succeed with whatever technical challenges you might have! Let me put a stake into the ground here and say that you simply cannot …
Read More -
You know the moment. CI goes red, or a build that took 8 seconds yesterday now takes 40, and you're staring at a wall of MSBuild output trying to find the one line that matters. The answer is almost always sitting in the bi Link to article: https://devblogs.microsoft.com/dotnet/msbuild-binlog-analyzer-vscode
Read More -
Traditional RAG hits a ceiling on analytical tasks that span hundreds of documents. This post shows how to use task-aware knowledge compression (TAKC) on AWS to pre-compress entire knowledge bases into task-specific representations, cache them at multiple fidelity tiers, and route each query to the right tier, with an …
Read More -
In this post, we cover why Deepgram built on IAM temporary delegation, how the integration works end-to-end, and what it unlocks for customers running Deepgram speech models on SageMaker AI. With this integration, Deepgram has reduced the time for initial investigation on a SageMaker AI support ticket from days to …
Read More